DeepSeek crashed again. Web and API both went down at the same time 🥲
DeepSeek crashed again
More posts
Get any agent to come to you first.
I wrote a prompt, put it on an hourly schedule, and ended up with something close to Muse's proactive messaging. The quality on Hermes genuinely surprised me: it only reaches out when it actually has high-value stuff to send. Can't show it in action without leaking personal info, but the prompt is yours to copy — schedule it and see what you get.
Cue from Manus is free for a limited time right now.
It's Manus's cloud agent product. No free tier normally, plans start at $20/mo for Pro, but access is free during the promo. Invite code: 4BSCU. Cue feels like grok-bot's playbook. Multi-agent with data isolation, and each agent even gets its own computer. You can group agents. Every agent ships with one free computer. More costs extra. The specs are decent, 8 cores and 15GB RAM. The catch is auto-sleep, so you still need the platform's native scheduled task to keep it alive. Works in the Cue app, and you can also hook it up to iMessage, Telegram, LINE, or Slack.
Claude appeal rejected.
Won't refund the subscription either. I'm half convinced the appeal email is itself phishing, because I'm pretty sure they log the IP. DHH came to Shenzhen recently and showed how he uses Claude Code over there. That's the safest way now, honestly: run Claude Code on an overseas machine, connect through Tailscale, never use it locally. So I need to rent an overseas box with a residential IP, and register and log into Claude there.
Sharing my current mobile only workflow.
Until late September it was the usual setup: parked in front of my laptop, terminal open, bossing pi around, fanning out subagents, then eyeballing diffs myself and filing the PR. Glued to the chair all day, every day. Late September I moved the whole thing to my phone, Hermes runs the show, pi takes the orders. My back is very grateful. Three weeks in, still no regrets. Stack: Hermes on flagship brains (gpt-6-astra / opus-5.5), pi on mid-tier (ds-v4.1-flash / sonnet / terra) with as few plugins as possible, the two talking over a2a. Hermes reads the issues, slices them into small tasks, spins up a worktree for each one, and dispatches a pi into it. When a pi finishes it pings Hermes, who decides: ship the PR or bounce it back for rework. I get back from a full day of being a tourist, or just wake up, and a dozen PRs are sitting there done. Pretty sweet. The catch is how black-box the whole thing is. My emotional arc has been a rerun of early vibe coding, except back then I at least read the diffs. Now even that goes to a flagship model. Boxes all the way down. If you don't have data anxiety, grok-bot and chatgpt-dot basically ship this out of the box, grok-cli and codex built in, native agent-to-agent comms. Downside: your code lives on their servers, everything's moderated, and one ban takes it all with it.
